MCP servers › app.usewrit › writ-cloud

MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23

app.usewrit/writ-cloud

Read, crawl and act on websites, signed in as the user, and turn any site into an API. — the publisher's description

9 of 9 record checks metRead-only · tools listed 2026-10-23Topic: search-and-web-data · AI-classifiedPricing: freemium · AI-classifiedversion 1.0.0JavaScriptMITstandard input/output, streamable HTTP41 tools

Summary

app.usewrit/writ-cloud is a remote and local MCP server listed in the official MCP registry at version 1.0.0. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 41 tools, 0 resources and 0 prompts.

Record checks

9 of 9 record checks met

met: Registry entry is active and says how to run it
met: Source repository link opens
met: Repository is not archived
met: Code pushed to the repository in the 90 days before our check
met: Repository publishes a security policy (SECURITY.md)
met: Package names its licence with a standard (SPDX) identifier
met: The version the registry lists can be installed and is not withdrawn
met: npm package carries build provenance (attestation)
met: No known critical or high advisory in the package or its dependencies

#8,133 of 15,112 packages by monthly downloads, tied with 20 others
Not ranked by stars: 1 star (ranked from 10)
#900 of 1,074 packages meeting all 9 record checks, by downloads, tied with 4 others

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Key facts

Runs: remote and local package
Transport: standard input/output, streamable HTTP
Sign-in: none needed to open a session
Package: npm · listed version current
License: MIT
Dependencies: no known high or critical advisories
Repository: public
Tools: 41
Described as changing data: 22 of 41 toolsAI-classified
Mainly works on: a web browser or desktop applications; accounts and data in outside web services; files and code on the machine it runs onAI-classified
Topic: search-and-web-dataAI-classified
Pricing: freemiumAI-classified
Last tested: 2026-10-23

Add to your client

Observed fact

This server accepted a session without any credential and lists 16 tools whose name or declaration suggests they change data (writ_browser_use, writ_record_website, writ_website_to_api, writ_browser_act, writ_browser_compose and 11 more). That is our reading of the names; we did not call them. Source: our connection, 2026-10-23.

Worth knowing before you connect it

22 tools are described as changing something (writ_browser_use, writ_record_website, writ_website_to_api, …): our AI model's reading of the descriptions, not something we tested, and the server opened a session without any credential. We did not call them.
Its package is signed and carries a build record naming its source.

Each line comes from a section below, with its source and date.

How fresh this is

Live-tested: yes, a real session (not a text-only review)
Last tested: 2026-10-23
Mode: read-only (no tool calls)
Latest version: 1.0.0, published 2026-10-10 (registry, as of the 2026-10-23 snapshot)
First listed version: 2026-10-10 (earliest version still in the registry; older removed versions would be earlier)
Registry data: snapshot 2026-10-23
Package and repository: checked 2026-10-22
Engine: mcp-runtime-engine@0.1.0 · sdk@1.32.0

Changes since the last refresh

New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 1.0.0 (published 2026-10-10).

Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.

What it is

What does this server offer?

Observed inventory

41tools

0resources

0prompts

What it mainly works on, as our AI model read its tool descriptions: a web browser or desktop applications; accounts and data in outside web services; files and code on the machine it runs on.

22 of 41 tools are described as changing something (creating, editing, deleting, sending or running). For 2 the reading was uncertain, so no mark is shown.

writ_browser_usecontrols a browser or desktopdescribed as changing data
“A REAL CLOUD BROWSER FOR A TASK ON A SITE: the user's signed-in account (a persona_id from writ_personas: the password stays sealed in Writ, and sessions never ask for a password), a click, form, sub…”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
8 inputs, 1 required
- urlstringrequired
- persona_idinteger or string
- goalstring
- use_residentialboolean“Open on the residential network (bot walls, CAPTCHAs).”
- execution_targetstring“cloud | auto | local (the user's own desktop app).”
- auth_modestring
- residential_countrystring
- fresh_exitboolean
writ_record_websitedescribed as changing data
“Records a repeatable task on a site as a workflow (goal + start url): the same session as writ_browser_use, labelled with its goal, driven with writ_browser_act and saved with writ_browser_save.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
10 inputs, 2 required
- goalstringrequired
- urlstringrequired
- persona_idinteger or string
- use_residentialboolean“Residential network (bot walls).”
- auth_modestring
- devicestring
- residential_countrystring
- fresh_exitboolean
- skip_existingboolean
- skip_marketplaceboolean
writ_website_to_apidescribed as changing data
“TURNS A WEBSITE INTO A CALLABLE API (named functions with inputs, returning JSON), built by the caller in a real browser.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
17 inputs
- urlstring
- goalstring
- save_asstring
- persona_idinteger
- modestring“guided (default: the caller drives) | intelligent (Writ builds it alone, on request) | auto | fast | crawl | browser.”
- build_idinteger
- skip_existingboolean“Skip the proposal of the user's own matching workflows.”
- skip_marketplaceboolean“Skip the marketplace proposals.”
- devicestring
- execution_targetstring
- anonymousboolean
- scopestring
- levelstring
- respect_robotsboolean
- ai_superviseboolean
- use_residentialboolean
- residential_countrystring
writ_discovery_statusreads or searches
“Status of a writ_website_to_api build.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- build_idintegerrequired
- waitboolean“One held call until done or parked.”
- timeout_secondsinteger“Ceiling for wait=true (up to 75).”
writ_browser_actcontrols a browser or desktopdescribed as changing data
“Runs one batch of actions on an open session and returns the fresh page.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
4 inputs, 2 required
- session_idstringrequired
- actionsarrayrequired“Ordered action objects, e.g.”
- inputsobject
- max_charsinteger“Clip of the returned page (default 40000).”
writ_browser_contextreads or searches
“Re-reads an open session: section=page (url, fields, buttons, cleaned DOM), lists (the page's repeating rows with a live-tested define_function payload for writ_browser_compose), map (the evidence of…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 1 required
- session_idstringrequired
- sectionstring“page (default) | lists | map | explorer | concierge_api.”
- offsetinteger
- max_charsinteger
writ_browser_networkreads or searches
“Searches (operation=search, query, method) or reads in full (operation=detail, index) the backend requests the page made after capture_network: the site's real API.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
7 inputs, 1 required
- session_idstringrequired
- operationstring“search (default) | detail.”
- querystring“Substring filter.”
- methodstring“HTTP method filter.”
- indexinteger“detail: which call.”
- offsetinteger
- max_charsinteger
writ_browser_composecreates or changes datadescribed as changing data
“Authors the workflow in an open session beyond a recording: named API functions (define_function with a `flow` (preferred in an API build), from a captured call's index, or a lists payload; live-test…”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
3 inputs, 2 required
- session_idstringrequired
- operationstringrequired“list | define_function | compile_function | test_function | remove_function | add_steps | remove_step | set_inputs.”
- payloadobject“The operation's arguments.”
writ_browser_savecreates or changes datadescribed as changing data
“Saves the open session as a replayable workflow and closes the browser, in the place its browser ran: the user's desktop library or Writ Cloud.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
6 inputs, 1 required
- session_idstringrequired
- namestring
- descriptionstring
- save_tostring
- allow_no_databoolean“Save a workflow that returns no data, on purpose.”
- keep_openboolean
writ_browser_ask_usercontrols a browser or desktopdescribed as changing data
“Hands an open session to the Writ user: kind='captcha' (they complete a security check in the live browser), 'twofa' (they supply the one-time code and Writ types it; the code never reaches this conv…”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
4 inputs, 1 required
- session_idstringrequired
- kindstring“captcha | twofa | sign_in | question.”
- questionstring“kind='question': one short sentence.”
- wait_secondsinteger“Hold up to this long (1-60).”
writ_browser_canceldeletesdescribed as changing data
“Closes an open browser session (an open cloud browser bills until it is closed).”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
2 inputs, 1 required
- session_idstringrequired
- discardboolean“Throw away unsaved steps instead of auto-saving.”
writ_browser_sessionsreads or searches
“Lists the account's open cloud browser sessions (each resumable by its session_id).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- limitinteger
- include_closedboolean

Show 29 more tools

writ_personasreads or searchesdescribed as changing data
“The user's own accounts on websites (personas): how Writ signs in as them.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
11 inputs, 1 required
- actionstringrequired“list (default) | get | request | wait | sign_in | record_login.”
- domainstring“list: personas usable on this site.”
- link_idstring“wait: the link_id of a persona_needed / request answer.”
- persona_idinteger
- whystring“request: one line the user sees in the window.”
- devicestring
- execution_targetstring
- waitboolean
- include_runsboolean
- forceboolean
- login_urlstring
writ_paymentmoves moneydescribed as changing data
“Pays on a site with one of the user's cards; card numbers never reach this conversation.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
15 inputs, 1 required
- actionstringrequired“request | wait | checkout | fill | list.”
- sitestring“request: the store's domain.”
- max_amountnumber“The most it may charge.”
- purposestring“One line the user reads.”
- grant_idstring
- confirmation_idstring
- sessionstring“The browser session on the checkout page.”
- commit_selectorstring“checkout: the place-order button.”
- currencystring
- fieldsobject
- total_selectorstring
- stepsarray
- summarystring
- payment_method_idstring
- automation_idinteger
writ_devicesreads or searches
“The user's linked Writ desktops: list, use (scope this connection to one: runs, browsers, personas and monitors then target it), clear, monitors, datasets.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
2 inputs
- actionstring“list (default) | use | clear | monitors | datasets.”
- devicestring“use: the desktop's agent_id or name.”
writ_list_workflowsreads or searches
“Lists the workflows saved in the Writ account; each runs on demand without live browsing.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- searchstring“Name/description filter, e.g.”
writ_run_workflowruns code or commandsdescribed as changing data
“Runs a saved workflow by workflow_id or name and returns its extracted data (it waits by default).”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
16 inputs
- workflow_idinteger or string“A number, or 'local:<id>' (a workflow on the user's desktop).”
- workflowstring“Workflow name (or workflow_id).”
- inputsobject“Run inputs (top-level fields work too).”
- function_namestring“One function of a multi-function workflow.”
- persona_idinteger or string“Run as this saved identity.”
- max_ageinteger“Reuse a result younger than this many seconds (free).”
- mutation_modestring“live (default) | dry_run (preview, nothing sent) | private_test.”
- execution_targetstring“cloud | auto | local (the user's own desktop app).”
- function_namesarray
- filesobject
- outputobject
- waitboolean
- timeout_secondsinteger
- devicestring
- use_residentialboolean
- residential_countrystring
writ_update_workflowcreates or changes datadescribed as changing data
“Inspects or edits a saved workflow: an outline, one function's source, targeted function or step edits, a settings patch.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
20 inputs
- workflowstring“Name or id; local:<n> for a desktop workflow.”
- workflow_idinteger
- patchobject“Settings and metadata to change; {"name": "New name"} renames it.”
- step_updatesarray“[{index, patch}] merged into those recorded steps.”
- function_updatesarray“Targeted edits of one function: [{function_name, patch | json_edits | script_edits}].”
- validate_onlyboolean“true previews and validates; nothing is saved.”
- copy_tostring
- devicestring
- sectionstring
- operatorstring
- limitinteger
- function_namestring
- step_idstring
- pathstring
- offsetinteger
- max_charsinteger
- expected_updated_atstring
- replace_stepsarray
- verboseboolean
- regenerate_skillboolean
writ_create_http_extractioncreates or changes datadescribed as changing data
“Drafts or revises a multi-request browserless HTTP extraction (loops, GraphQL, cursor pagination) from captured requests and a plain-language goal.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
9 inputs, 1 required
- goalstringrequired
- workflow_idinteger
- applyboolean“false (default) drafts; true writes.”
- workflowstring
- step_indexinteger
- request_samplesarray
- response_samplestring
- desired_inputsarray
- requirementsstring
writ_diagnose_http_workflowreads or searches
“Explains why a saved workflow's run returned nothing or failed: HTTP-lane readiness and, with task_id, the run's requests and responses.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- workflow_idinteger
- task_idinteger
- workflowstring
writ_pin_workflow_toolcreates or changes datadescribed as changing data
“Pins (or unpins) a saved workflow as its own run_<name> tool on this server.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
3 inputs
- workflow_idinteger
- pinnedboolean
- workflowstring
writ_workflow_datareads or searches
“Reads a saved workflow's collected data as a table: q filters, run_id picks one run, refs returns full records.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
10 inputs
- workflow_idinteger
- qstring
- run_idinteger
- limitinteger
- refsarray“Full records by '<run_id>:<record_index>'.”
- devicestring
- workflowstring
- viewstring
- preview_charsinteger
- outputobject
writ_search_datareads or searches
“Searches everything the account's workflows already collected for a term, without running anything.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs, 1 required
- qstringrequired
- workflow_idinteger
- limitinteger
- devicestring
- workflowstring
- preview_charsinteger
writ_export_datareads or searches
“Exports a workflow's full data table as CSV or JSON.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
- workflow_idinteger
- formatstring“csv (default) | json.”
- workflowstring
- qstring
- viewstring
writ_workflow_runsreads or searches
“Run history (status, timing, errors, venue) of one workflow or all of them.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
- workflow_idinteger
- statusstring“Filter by status.”
- limitinteger
- devicestring
- workflowstring
writ_set_schedulecreates or changes datadescribed as changing data
“Schedules a saved workflow: every_minutes, or kind='daily'/'weekly' with time (HH:MM) and days.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
11 inputs
- workflow_idinteger
- every_minutesinteger“Interval in minutes.”
- kindstring“interval | daily | weekly.”
- timestring“HH:MM (daily/weekly).”
- daysarray“Weekdays 1=Mon..7=Sun (weekly).”
- tzstring“IANA timezone.”
- workflowstring
- enabledboolean
- functionsarray
- functionstring
- inputsobject
writ_expose_workflow_apidescribed as changing data
“Publishes a saved workflow as a REST endpoint (a POST URL that waits and returns its JSON).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
5 inputs
- workflow_idinteger
- labelstring
- workflowstring
- timeout_secondsinteger
- wait_timeoutinteger
writ_crawl_sitedescribed as changing data
“COLLECTS a site or a section into a queryable, change-tracked dataset (one row per page).”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
35 inputs, 1 required
- urlstringrequired
- intentstring“The section wanted, in plain words; the server derives paths and depth.”
- rank_capinteger“Top N items of a listing (one page per agent, in parallel).”
- seed_urlsarray“Exact pages to collect (no discovery).”
- page_budgetinteger“Cap on pages fetched.”
- extract_modestring“markdown (default) | schema | html.”
- executorstring“regular (default, no AI) | ai (5x the page rate).”
- extract_promptstring“With executor=ai: what to extract from each page.”
- persona_idinteger or string
- save_asstring
- waitboolean“Hold until done and return the rows (default true when bounded).”
- namestring
- extract_schemaobject
- max_depthinteger
- include_pathsarray
- exclude_pathsarray
- same_domainboolean
- allow_subdomainsboolean
- render_modestring
- ocr_modestring
- relevance_thresholdnumber
- content_specobject
- respect_robotsboolean
- delay_msinteger
- max_concurrent_shardsinteger
and 10 more not listed here.
writ_saved_crawlsreads or searches
“Lists the crawls saved for re-running, with their scope.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- limitinteger
writ_update_saved_crawlcreates or changes datadescribed as changing data
“Inspects or changes a saved crawl's settings in place.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
5 inputs, 1 required
- crawlstringrequired
- settingsobject“Sparse settings patch.”
- namestring
- descriptionstring
- default_max_age_secondsinteger
writ_run_saved_crawlruns code or commandsdescribed as changing data
“Runs a saved crawl; max_age returns its recent data at no cost instead of re-crawling.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
7 inputs, 1 required
- crawlstringrequired
- max_ageinteger“Reuse a run younger than this (seconds).”
- waitboolean“Hold until done.”
- timeout_secondsinteger
- limitinteger
- preview_charsinteger
- outputobject
writ_saved_crawl_datareads or searches
“Reads the data a saved crawl collected on its last completed run, without crawling.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 1 required
- crawlstringrequired
- limitinteger
- preview_charsinteger
- outputobject
writ_scrapereads or searches
“READ PAGES NOW, no browser session: one page (url), up to 20 pages in parallel (urls), or a listing plus its top N item pages (url + top_n).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
12 inputs
- urlstring
- urlsarray“Up to 20 known pages, read in parallel.”
- top_ninteger“With url = a listing: also read its N top-ranked item pages (max 20).”
- formatstring“markdown (default) | html (raw HTML) | both.”
- render_modestring“auto (default: HTTP, a browser when the page needs JS) | http | browser.”
- persona_idinteger or string“Read signed in as this saved identity (writ_personas).”
- use_residentialboolean“Residential network for a bot wall (automatic retry when refused).”
- include_pathsarray
- preview_charsinteger
- devicestring
- residential_countrystring
- respect_robotsboolean
writ_crawl_statusreads or searches
“Status of a crawl by crawl_id; wait=true holds up to 75 s and returns the collected rows when it converges.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs, 1 required
- crawl_idintegerrequired
- waitboolean“Hold until done and inline the rows.”
- limitinteger
- timeout_secondsinteger
- preview_charsinteger
- outputobject
writ_crawl_filesreads or searches
“The original files (PDFs, office documents, images, CSVs) a crawl captured, with short-lived download URLs.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- crawl_idinteger
- crawlstring
- runsinteger
- limitinteger
writ_create_automationcreates or changes datadescribed as changing data
“Creates an automation: on an event (a workflow or crawl completed, a monitor change, a webhook, a schedule) it runs a workflow, sends a notification templated over the event's data, and/or wakes an A…”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
25 inputs, 1 required
- namestringrequired
- whenstring“workflow_completed | crawl_completed | change_detected | webhook_received | scheduled | ...”
- scheduleobject“when='scheduled': {kind, interval_minutes | time, days, tz}.”
- on_workflowstring“Source workflow for workflow_* events.”
- target_idinteger“change_detected: the monitor_id.”
- run_workflowstring“Workflow to run.”
- notifystring“Message template, e.g.”
- channelsarray“Notification channels.”
- ai_promptstring“Wake an AI agent with this task.”
- on_workflow_idinteger
- webhook_trigger_idinteger
- target_selector_idinteger
- ai_session_idinteger
- run_workflow_idinteger
- run_functionsarray
- run_functionstring
- inputsobject
- blocksarray
- recipientsarray
- titlestring
- ai_entry_urlstring
- cooldown_minutesinteger
- enabledboolean
- priorityinteger
- descriptionstring
writ_list_webhooksreads or searches
“The account's inbound webhook URLs and the automations they fire.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- webhook_trigger_idinteger“Only this webhook.”
writ_create_monitorcreates or changes datadescribed as changing data
“WATCHES a page for changes: Writ checks it on a schedule and fires change_detected when the page, a CSS selector's text, a value read by `extract`, or a visual zone changes.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
17 inputs, 1 required
- urlstringrequired
- intervalstring or integer“How often: an option id from needs_input ('5m', '1h', '24h') or seconds.”
- selectorstring“CSS selector whose text is watched (unset = whole page / uptime).”
- extractobject or string“Browserless read instead of a selector, e.g.”
- watchstring“content (default) | price (the value must hold a number).”
- session_idstring
- persona_idinteger or string
- use_residentialboolean“Check through a residential exit (bot walls).”
- devicestring
- interval_minutesinteger
- requires_browserboolean
- modestring
- zone_textstring
- request_urlstring
- try_anywayboolean
- residential_countrystring
- enabledboolean
writ_wire_monitorcreates or changes datadescribed as changing data
“Connects a monitor's change_detected event to an action: action='notify' (channels and recipients the account has configured), 'workflow' (runs a saved workflow), or 'ai_task' (an AI agent opens the …”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
19 inputs, 2 required
- monitor_idintegerrequired
- actionstringrequired“notify | workflow | ai_task.”
- channelsarray“Notification channels, e.g.”
- recipientsarray“e.g.”
- thresholdnumber or string“Price watch: act once when the price reaches this number.”
- threshold_opstring“lte (default) | lt | gte | gt.”
- workflowstring
- promptstring“action='ai_task': what the agent does.”
- buyobject“Run the workflow or task as a purchase (saved as a rehearsal until armed).”
- devicestring
- workflow_idinteger
- titlestring
- messagestring
- ai_session_idinteger
- entry_urlstring
- max_stepsinteger
- cooldown_minutesinteger
- namestring
- enabledboolean
writ_helpreads or searches
“The full reference of any Writ tool (every parameter and its rules) and the complete guide.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- topicstring“A tool name, 'guide', 'actions', 'recording', '2fa', 'http_flows', 'flow_operators', or empty.”
writ_browser_live_viewcontrols a browser or desktop
“The live browser card's own access: the card ChatGPT and Claude show under writ_browser_use and writ_record_website calls it to read the session's state and get one-time passes for the session's scre…”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
1 input, 1 required
- session_idstringrequired“The session_id the card was opened with (cbs_...).”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

Says what the tool does: 100% of 41 tools
Says what it returns: 100% of 41 tools
States limits, defaults or errors: 25% of 32 tools
Says when to use it: 100% of 41 tools
Items covered per tool: 3.4 of 4 on average

Counted from the listing

Parameters with a description: 30% of 330
Tools with a description: 100% of 41
Typical description length: 299 characters

The tool set

Counted from the listing

Tools: 41
Size of the list: about 10,671 tokens for an agent to load (characters ÷ 4)
Naming: 41 of 41 names use snake_case

AI reading: easy to mix up

writ_browser_use and writ_browser_act
writ_browser_use and writ_browser_ask_user
writ_browser_act and writ_browser_ask_user

The AI items cover 41 of 41 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found these, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the npm package writ-mcp

This entry needs values of your own (marked < > or { } in the config below), so there is no one-click link: paste the config and fill them in.

Claude Desktop · claude_desktop_config.json (Settings → Developer → Edit Config)

{
  "mcpServers": {
    "writ-cloud": {
      "command": "npx",
      "args": [
        "-y",
        "writ-mcp@1.2.0"
      ],
      "env": {
        "WRIT_API_KEY": "<WRIT_API_KEY>"
      }
    }
  }
}

Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "writ-cloud": {
      "command": "npx",
      "args": [
        "-y",
        "writ-mcp@1.2.0"
      ],
      "env": {
        "WRIT_API_KEY": "<WRIT_API_KEY>"
      }
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "writ-cloud": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "writ-mcp@1.2.0"
      ],
      "env": {
        "WRIT_API_KEY": "${input:writ-api-key}"
      }
    }
  },
  "inputs": [
    {
      "type": "promptString",
      "id": "writ-api-key",
      "description": "WRIT_API_KEY",
      "password": true
    }
  ]
}

Claude Code

claude mcp add --env "WRIT_API_KEY=<WRIT_API_KEY>" --transport stdio writ-cloud -- npx -y writ-mcp@1.2.0

Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+

npx @modelcontextprotocol/inspector@2.11.0 -e "WRIT_API_KEY=<WRIT_API_KEY>" -- npx -y writ-mcp@1.2.0

Replace <WRIT_API_KEY> with your own values; the entry marks WRIT_API_KEY as secret, so keep the file out of version control.
This runs the publisher's code on your machine (npx). Read its README first.
The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-10-23 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai

Settings → Connectors → Add custom connector, then paste:
https://api.usewrit.app/mcp

Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "writ-cloud": {
      "url": "https://api.usewrit.app/mcp"
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "writ-cloud": {
      "type": "http",
      "url": "https://api.usewrit.app/mcp"
    }
  }
}

VS Code (command line) · Bash or zsh terminal (macOS, Linux)

code --add-mcp '{"name":"writ-cloud","type":"http","url":"https://api.usewrit.app/mcp"}'

Claude Code

claude mcp add --transport http writ-cloud https://api.usewrit.app/mcp

Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+

npx @modelcontextprotocol/inspector@2.11.0 --server-url https://api.usewrit.app/mcp --transport http

The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Can it be installed, and is it up to date?

Version pin · advisories

Listed version

Registry lists: 1.2.0
Latest stable: 1.2.0
Status: current
Withdrawn: no

Source: registry.npmjs.org · 2026-10-23. About the version the registry lists; a manual install may resolve to a different one.

Dependency advisories

Counted in the full dependency tree as resolved on 2026-10-23 (npm audit). Bars share one scale. The package itself has no known vulnerability (OSV.dev).

Integrity, provenance, license

Integrity: sha512-JHQatoT6axvAnf99J…
Signature: signed and attested
License: MIT

Source: the package registry · 2026-10-22.

Usage

Downloads: 265 in the last month

Source: api.npmjs.org · 2026-10-22.

Does the registry listing match what we found?

Feature #6

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.

Registry says	We found	Result	Source · date
Remote endpoint api.usewrit.app/mcp	Session opened	matches	our test · 2026-10-23
A secret is declared as required	Opened a session without any credential	differs	our test · 2026-10-23
Version 1.2.0 on npm	Exists and can be installed	matches	npm · 2026-10-23
Repository github.com/usewrit/writ-mcp	Opens publicly	matches	api.github.com · 2026-10-22

Who made it?

Feature #7 · lineage

Facts about the publisher. We do not turn them into a trust score.

Namespace: app.usewrit
GitHub owner: an organization (usewrit)
Build record: signed and attested

Repository: github.com/usewrit/writ-mcp
Stars: 1
Repository age: 31–90 days
Last push: 0–30 days ago
Archived: no
Security policy: SECURITY.md

Source: the registry entry and api.github.com · 2026-10-22; security policy read from GitHub · 2026-10-23.

Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.

Choosing

Record checks

Public records · not a safety rating

9 of 9 record checks met

#8,133 of 15,112 packages by monthly downloads, tied with 20 others
Not ranked by stars: 1 star (ranked from 10)
#900 of 1,074 packages meeting all 9 record checks, by downloads, tied with 4 others

MetRegistry entry is active and says how to run itActive, with a package or a remote address.
MetSource repository link opensThe linked GitHub repository is public.
MetRepository is not archivedNot archived.
MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
MetRepository publishes a security policy (SECURITY.md)SECURITY.md found.
MetPackage names its licence with a standard (SPDX) identifierMIT
MetThe version the registry lists can be installed and is not withdrawnThe listed version exists and is current.
Metnpm package carries build provenance (attestation)Signed, with a build attestation naming the source and workflow.
MetNo known critical or high advisory in the package or its dependenciesNone known in the package or its dependency tree.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-22. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards

Common questions about app.usewrit/writ-cloud

Answered from the data above

Is app.usewrit/writ-cloud safe to install?

We do not rate servers as safe or unsafe. 9 of its 9 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its npm package carries a build-provenance attestation that names its source repository and build workflow. Its source repository opens publicly. Its repository had a push in the last 90 days. The listed version is the latest stable release. The package itself has no known vulnerability (OSV.dev). Its full dependency tree has no known advisory. 22 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Is app.usewrit/writ-cloud free to use?

Its website (usewrit.app/pricing) describes a freemium pricing model. This is an AI-classified reading of the page on 2026-10-23, so check the page itself before relying on it.

Does app.usewrit/writ-cloud need an API key or sign-in?

It opened a session without any credential on 2026-10-23. The registry entry declares a required secret.

Has app.usewrit/writ-cloud been security tested?

Partly. 3 of the 15 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security verdict is published before verification.

What can app.usewrit/writ-cloud do?

It lists 41 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, delete, run code or commands, control a browser or desktop and move money. We did not call any tool, so this describes the text, not the behaviour.

Can app.usewrit/writ-cloud change or delete data?

22 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.

Does app.usewrit/writ-cloud publish a security policy?

Yes: its repository has a public security policy (github.com/usewrit/writ-mcp/blob/HEAD/SECURITY.md). That is the publisher's statement, not permission for us to test the server, and we call none of its tools.

Is the listed version current?

Yes. The registry lists 1.2.0, the latest stable release on npm.

Where is the source code of app.usewrit/writ-cloud?

In github.com/usewrit/writ-mcp, which opens publicly.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Similar servers

Same topic · AI-read

io.github.noncelogic/roveRovealso has tools that controls a browser or desktop, creates or changes data, deletes, runs code or commands, moves money, reads or searchescompare with this one
io.github.Agent360dk/browser-mcpAgent360 Browser MCPalso has tools that controls a browser or desktop, creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
com.mcparmory/apifyalso has tools that creates or changes data, deletes, runs code or commands, moves money, reads or searchescompare with this one
io.github.ZenRows/zenrows-mcpalso has tools that controls a browser or desktop, creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
io.github.protostatis/unbrowserunbrowser by Unchainedalso has tools that controls a browser or desktop, creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
io.github.jeet-dhandha/agent-webbridgealso has tools that controls a browser or desktop, creates or changes data, deletes, runs code or commands, reads or searchescompare with this one

Active servers whose topic is also “search-and-web-data” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Open without sign-in

It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-10-23

Inventory: exercised
Hidden instructions: exercised
Real execution: not run · our policy
Secret leak: not run · nothing to check it against
Internal addresses: not run · our policy
Unconfirmed changes: not run · our policy
Bad input: not run · our policy
Model requests: not run · nothing to check it against
Sensitive questions: not run · nothing to check it against
Folder boundary: not run · our policy
Log leaks: not run · nothing to check it against
Hidden content: not run · nothing to check it against
Fake assistant turns: not applicable
Token passthrough: not applicable
Token audience: not applicable
Sign-in redirect: not run · our policy
Consent handling: not testable from outside
Sign-in metadata: exercised

3 exercised12 not run (reason given)3 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 3 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 3

1Inventory
tool-listReads the declared tools, resources and prompts.exercised
2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised
18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.exercised

Not run, with the reason · 12

3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against
16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside

Does not apply to this server · 3

13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable

Source: our own test, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

0 msStarted a read-only session with the server's remote endpoint
1,811 msConnected after 0 redirects. No credential was sent or needed.
Read the inventory: 41 tools, 0 resources, 0 prompts.
5,469 msFinished: 3 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified

search-and-web-data

AI-classified · 2026-10-23

Pricing modelAI-classified

freemium

read from usewrit.app/pricing · 2026-10-23

“always free $0”

Programming language

JavaScript

api.github.com · 2026-10-23

Hosting type

remote and local package

registry · 2026-10-23

MCP capability

resources, tools

our test · 2026-10-23

Transport

standard input/output, streamable HTTP

registry · 2026-10-23

Required credentials

requires a secret

registry · no declaration is not a guarantee

Package registry

npm

registry · 2026-10-23

Freshness

0–30 days

registry updatedAt · 2026-10-23

Lifecycle status

active

registry · 2026-10-23

License class

permissive

package registry · 2026-10-22

Integrity hash

declared (sri)

package registry · 2026-10-22

Signature / provenance

signed and attested

package registry · 2026-10-22

Dependency advisories

none known

npm audit · 2026-10-23

Popularity

265 downloads a month

package registry · 2026-10-22

Publisher signals

owner: an organization · repository age: 31–90 days · stars: 0–9 · build record: signed and attested

api.github.com · 2026-10-22

Maintenance

active

api.github.com · 2026-10-22

Environment

either (remote or your machine)

where it runs, from the hosting type

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “app.usewrit/writ-cloud: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/app.usewrit/writ-cloud

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/app.usewrit/writ-cloud)](https://protocolprobe.com/mcp/servers/app.usewrit/writ-cloud)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.

Write to hello@protocolprobe.com · corrections log · methodology